Updated
Updated
Items with an AI score under 20 are hidden. Show low-relevance items
ClaudeDevs@ClaudeDevsOfficialAI score29AIAnthropic is adding pre-built sample mods to the Claude Code Playground repo for developers to adapt. The post points readers to a getting started guide on creating Claude Code mods.
ClaudeDevs@ClaudeDevsOfficialAI score34AIAnthropic's ClaudeDevs introduced Blast Radius, which catches risky shell commands such as rm -rf, git reset --hard, or a force push before they execute. It displays what the command would affect in a side pane.
Databricks@databricksOfficialAI score20AIDatabricks' Smart Routing evaluates each coding task separately and selects the lowest-cost model capable of handling it, balancing quality, latency, and cost. In a demo, Omnigent splits an app build into planning, backend, and frontend work, routes each part to a different model, and runs some tasks in parallel.
Josh Woodward@joshwoodwardXAI score34AIGoogle has introduced the @google/stitch CLI, letting users generate screens and design systems without leaving the terminal. It connects to local coding agents and can send a local dev server snapshot to Stitch. The tool complements the existing Stitch MCP and SDK, and can also be driven through agents such as Antigravity.
Lewis Tunstall @ COLM 🌉@_lewtunXAI score44AIHugging Face shows that training LFM2.5-2.6B with RL inside the agent harnesses themselves lifted held-out task success from 42% to 54% across four harnesses. Before training, the model solved 62% of tasks in Mini-SWE-Agent but only 33% in Claude Code, so the same model behaved very differently per harness. The approach uses an OpenEnv capture proxy to record tokens and logprobs, Harbor for tasks and sandboxes, and TRL's async GRPO trainer, with 31% fewer tool calls on already-solved tasks; training in OpenCode alone mostly improved OpenCode.
Runway@runwaymlOfficialAI score36AIRunway introduced Visual Thinking, a new harness for coding agents that uses a real-time video model to visualize each step and tool call as it happens. The visualization lets users stay in the loop during complex autonomous workflows.
AIPareto 26.10 Preview is a multimodal composite model built for research, coding, and agentic workflows. It is described as delivering frontier-level performance across a broad range of general-purpose tasks, though the source excerpt is a preview and provides no benchmark scores, parameter counts, pricing, or availability details.
AIJetBrains has opened the Early Access Program for Air, an agentic development experience available as a plugin on JetBrains Marketplace or in the 2026.3 EAP builds of its IDEs. Air works with existing agents such as Codex, GitHub Copilot, Junie, and Cursor, and it ships with no agents installed. Free Junie Lite runs are offered, while cloud runs require a JetBrains AI subscription.
Why it matters: The post explains how Air brings existing agents into the IDE, showing a concrete workflow for managing parallel agent sessions alongside code review tools.
AIBarclays is expanding its collaboration with Anthropic to roll Claude out across its global operations, with Claude Code expected to reach 50% of its developer population by the end of 2026. Its Colleague Knowledge Assistant, powered by Claude through retrieval-augmented generation, has been used by more than 16,000 colleagues and handled over one million searches. In Global Markets, Claude models classify and route roughly 120,000 client emails daily.
AIManus has launched Game Dev in Manus 2.0, a feature that lets users with no coding experience build games with a real-time tweak panel, asset management, and multiplayer servers. The tweak panel lets users adjust settings such as speed, gravity, damage, and spawn rate while playing. Manus also handles much of the multiplayer infrastructure, including server deployment and networking, so games can be shared and played with friends.
Hamel Husain@HamelHusainXAI score38AIHamel Husain has published a longer review of a new Claude Auto Eval plugin after many users asked about it. He invites readers to share their experiences using the plugin and how it went for them. The plugin is part of Claude's ability to help build evaluations and hillclimb on them, as described by @ClaudeDevs.
indigo@indigoxXPickAI score81AIGoogle has announced Gemini 4 Argon, initially available only to trusted cyber defenders through its Fairwind Program while US government approval is pending. The author says the model is aimed at long-running software engineering, enterprise knowledge work, and cybersecurity tasks, with a 1 million token output limit. The post also gives promotional pricing of $2 per million input tokens and $10 per million output tokens, rising to $4 and $20 afterward, alongside a benchmark comparison.
Why it matters: The post places Gemini 4 Argon's benchmark table beside GPT-6 Astra and Claude models, showing where each leads across coding, knowledge work, and cybersecurity tasks.
Varun Mohan@_mohansoloXAI score25AIVarun Mohan says Gemini 4 Argon is doing well on the AA Coding Agent Index when run with the Antigravity harness. He notes that real-world usage matters more than benchmarks and promises more to come.
AIUnder equal time budgets and the same frontier LLM backbone, a single session of a minimal-harness coding agent with read, write, and bash primitives matched open-source state-of-the-art autonomous machine learning engineering harnesses. Apple researchers found the added orchestration and retrieval machinery redundant in large-scale ablation studies, pointing to the backbone model as the main driver of performance. They conclude that hand-crafted harnesses around strong models yield poor returns on current MLE benchmarks.
Vercel Developers@vercel_devOfficialAI score32AIAnt Ling's Ling 3.1 Flash is now available on Vercel AI Gateway, free through October 13. The model is built for coding and multi-step analysis.
koray kavukcuoglu@koraykvXPickAI score62AIGoogle is sharing Gemini 4 Argon first with trusted defenders in its Fairwind Program, with frontier capabilities in coding, knowledge work, and cyber security defense. The model is also being rolled out to the US government, and the company plans broader availability as testing progresses and safeguards allow.
Why it matters: The author is a Google DeepMind leader announcing the model directly, so the rollout limits to trusted defenders and government are the key detail to note.
Varun Mohan@_mohansoloXAI score40AIGoogle announced Gemini 4 Argon, a new frontier model that delivers frontier performance across complex software tasks, according to Varun Mohan. Thousands of Googlers have been using it internally in Antigravity, and it is rolling out first to trusted cyber defenders in the Fairwind Program, with broader availability to follow as soon as possible.
Google AI@GoogleAIOfficialPickAI score72AIGoogle AI announced Gemini 4 Argon, a new frontier model built for deep reasoning across long, complex workflows in software engineering, legal and finance knowledge work, and cybersecurity defense. Google says it is expanding the model's output token limit to 1M tokens. Argon is rolling out first to trusted cyber defenders in the Fairwind Program, with broader availability to follow as soon as possible.
Why it matters: The benchmark table compares Gemini 4 Argon against GPT-6 Astra and Claude models across knowledge work, coding, and multimodal tasks, showing where it leads and trails.
AIGoogle DeepMind announced Gemini 4 Argon, rolling out first to trusted cyber defenders through its Fairwind Program. Argon will launch at an introductory price of $2 per million input tokens and $10 per million output tokens, with output limits raised to 1M tokens. The post cites a 77.9% score on DeepSWE v1.1 and 91.7% on LVBench, and says broad availability will follow safeguard testing.
Why it matters: The post pairs Argon's benchmark claims with the phased release, pricing, and safeguard details, helping readers weigh its frontier-level capabilities against its access limits.
Microsoft Copilot@MSFTCopilotOfficialAI score23AIMicrosoft's new Copilot brings Home, Code, and Autopilot together in one place for creating custom apps, building decks, automating workflows, and resuming work. Users can start using the Copilot app now and try new features as they become available in Frontier.
AIGoogle announced Gemini 4 Argon, a new frontier model rolling out first to trusted cyber defenders through its Fairwind Program. The model's output limit rises to 1M tokens from 64K, and its introductory API price is $2 per million input tokens and $10 per million output tokens. Google says broader availability to developers, enterprises, and consumers will follow after more testing of guardrails.
Why it matters: The post pairs benchmark claims with a phased access plan, pricing, and safety measures, which helps readers judge how quickly Argon may reach developers.
merve@mervenoyannXAI score30AIHugging Face's Merve Noyan announced ml-intern, an open-source harness for ML engineering and research that she says is better than a coding agent. It is available to try in Hugging Face Chat.
eric zakariasson@ericzakariassonXAI score22AICursor's Eric Zakariasson announced engineering bots available in the Grok bot marketplace on x.ai. The bots can hand off coding tasks to Cursor, manage pull requests through GitHub and Origin plugins, and share video demos of what they build.
Grok Bot@botOfficialAI score31AIGrok Bot can now hand off coding tasks to Cursor, manage pull requests through GitHub and Origin plugins, and share video demos of what it builds. The post describes these additions as making the bot more powerful for building software.
Fireworks@FireworksAI_HQOfficialAI score34AIFireworks AI has made GLM 5.3 Flash available for training through its Serverless Training API, open to all users. The model supports both vision and text inputs. Fireworks says it performs well on its benchmarks for agentic coding, document analysis, and tool use while remaining cost-efficient to serve.
Cline@clineOfficialAI score34AICline says its desktop app can keep running on a laptop while the agent executes on any Linux machine reachable via SSH, configured under Settings → Remote. The setup requires no root access, no npm, and no public port, uploading a self-contained helper and tunneling only the authenticated Cline protocol.
eric zakariasson@ericzakariassonXAI score36AICursor's Eric Zakariasson shared a game-builder skill he has been using to build games with new models. The skill can be installed with the command npx skills add ericzakariasson/skills --skill game-builder.
GitHub@githubOfficialAI score42AIProject HydraFusion is now available in the GitHub Copilot app and VS Code, where users can select it like any other model. Behind the scenes, it routes a task across multiple models to draft, critique, revise, or escalate, then returns one combined result.
Ant Ling@AntLingAGIOfficialAI score31AIAnt Ling can convert plain-language prompts into standalone, interactive Three.js pages covering topics such as an internal combustion engine, an optical-disc reader, paramecium organelles, and vector-field divergence. The output is runnable code rather than just an explanation.
Ant Ling@AntLingAGIOfficialAI score38AIAnt Ling reports that its Ling-3.1-flash model completed a roughly 20-hour Rust port of a C image library. After a performance regression caused by busy-waiting workers and a parallelism adjustment, the model recovered and reached an 8.015× speedup. All 30 correctness checks passed.
Ant Ling@AntLingAGIOfficialAI score22AILing-3.1-flash achieved a 1.432x speedup on Pyright 1.1.400 while passing all 2,279 checks. The chart shows Claude Fable 5 at 1.502x and GLM-5.3-Flash at 1.290x, a close result on a real codebase with correctness intact.
Ant Ling@AntLingAGIOfficialAI score38AILing-3.1-flash built a Lua-to-x86-64 ELF compiler from scratch in about 17 hours, passing 178 of 182 tests for 97.8%. That is within 1.2 percentage points of the 99.0% shown for Claude Fable 5 and above GLM-5.3-Flash at 95.9%.
Ant Ling@AntLingAGIOfficialAI score22AILing-3.1-flash ranks #2 in the Mobile App (react native) category on Design Arena's Open Weights leaderboard, with 1,207 Elo. It also ranks #4 in SVG with 1,271 Elo among models added in the last 30 days.
DeepSeek Harness@DeepSeekHarnessXAI score62AIDeepSeek releases the DeepSeek Harness v0.2 preview with a desktop app for macOS and Windows. The release adds a plugin manager for installing, disabling, and uninstalling plugins without terminal commands, plus an experimental creator mode that generates plugins from user descriptions. The company says DeepSeek Harness is now the most widely used coding agent among users of the official DeepSeek API by DAU and daily sessions.
Google Gemini@GeminiAppOfficialAI score45AIGemini can build custom skills from chats and apply a saved skill automatically when a prompt matches it. Multiple skills can be stacked for larger tasks, such as combining a personal writing style skill with a brand guidelines skill. Starting today, skills can include reference files such as plain text documents, PDFs, or images, with sharing and Google Drive file support coming soon.
howie.serious@howie_seriousXAI score22AILocal and desktop agents such as Claude Code and Codex are powerful largely because they can use the shell, which connects them to the whole CLI ecosystem. The post lists tools including git, ffmpeg, curl, pandoc, gh, cron, and ssh as examples. It also says the video itself was produced by an agent operating the shell.
AICloudflare has released Auto Router in public beta through AI Gateway, where setting the model to cloudflare/auto routes each request to a model judged capable enough for the task. Internal tests showed up to 30% cost savings against frontier models, and on a 97-task internal benchmark cloudflare/auto scored 86.6% at $0.0084 per success versus 96.6% at $0.0210 for Claude Opus 5.5. The router is free during beta.
Why it matters: The source gives a benchmark table of success rates and costs per trial, showing how routing trades quality against price for a gateway deployment.
Qwen@Alibaba_QwenOfficialAI score34AIAlibaba's Qwen3.8-27B, a 27B dense model, is now accessible via Nebius Token Factory. Nebius describes it as suited to coding, deep research, and agent workflows, with a focus on planning and completing multi-step tasks.
Karl's AI Watts@aiwartsXAI score38AIKarl's AI Watts asks whether a menu-bar tool can switch models while preserving the existing conversation, so users avoid re-explaining their project each time. The post frames this as the reason they want to keep the menu bar tool, which the quoted post describes as magpie, a menu-bar switcher for 20+ agents including Claude Code and Codex that also offers a local gateway.
AIFactory's Automations, now generally available, let users describe a recurring workflow, set a schedule or event trigger, and have its Droid run it, with the model chosen per task. Templates cover ticket-to-PR, code review, security audits, PR babysitting, and morning Slack briefs. Among enterprise organizations using Automations in the past 30 days, 52% used automated code review, 48% used security review, and 35% used AutoWiki.